Autotrain compatible Axolotl Base model:microsoft/phi-2 Base model:quantized:microsoft... Conversational Custom code Dataset:whiterabbitneo/wrn-cha... Dataset:whiterabbitneo/wrn-cha... Endpoints compatible Generated from trainer Gguf Lora Phi Pytorch Q4 Quantized Region:us Safetensors Sharded Tensorflow
Phi2 Bunny Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Phi2 Bunny Parameters and Internals
| LLM Name | Phi2 Bunny |
| Repository 🤗 | https://huggingface.co/justinj92/phi2-bunny |
| Base Model(s) | |
| Model Size | 2.8b |
| Required VRAM | 5.6 GB |
| Updated | 2024-11-21 |
| Maintainer | justinj92 |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | q4|gguf|q4_k|q5_k |
| Model Architecture | AutoModelForCausalLM |
| License | mit |
| Model Max Length | 2048 |
| Is Biased | none |
| Tokenizer Class | CodeGenTokenizer |
| Padding Token | <|endoftext|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | dense|k_proj|v_proj|fc2|q_proj|fc1 |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 64 |
Best Alternatives to Phi2 Bunny
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi2 Sqlcoder | 0K / 5.6 GB | 156 | 6 |
| Zephyr Rag Agent Webgpt | 0K / 40.1 GB | 15 | 1 |
| Phi 2 Electrical Engineering | 0K / 5.6 GB | 71 | 17 |
| Phi Med V1 | 0K / 11.1 GB | 6 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than justinj92/phi2-bunny .
Rank the Phi2 Bunny Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 38199 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110